A deep learning approach to direct immunofluorescence pattern recognition in autoimmune bullous diseases.

BACKGROUND: Artificial intelligence (AI) is reshaping healthcare, using machine and deep learning (DL) to enhance disease management. Dermatology has seen improved diagnostics, particularly in skin cancer detection, through the integration of AI. However, the potential of AI in automating immunofluorescence imaging for autoimmune bullous skin diseases (AIBDs) remains untapped. While direct immunofluorescence (DIF) supports diagnosis, its manual interpretation can hinder efficiency. The use of DL to classify DIF patterns automatically, including the intercellular (ICP) and linear pattern (LP), holds promise for improving the diagnosis of AIBDs. OBJECTIVES: To develop AI algorithms for automated classification of AIBD DIF patterns, such as ICP and LP, in order to enhance diagnostic accuracy, streamline disease management and improve patient outcomes through DL-driven immunofluorescence interpretation. METHODS: We collected immunofluorescence images from skin biopsies of patients suspected of having an AIBD between January 2022 and January 2024. Skin tissue was obtained via a 5-mm punch biopsy, prepared for DIF. Experienced dermatologists classified the images as ICP, LP or negative. To evaluate our DL approach, we divided the images into training (n = 436) and test sets (n = 93). We employed transfer learning with pretrained deep neural networks and conducted fivefold cross-validation to assess model performance. Our dataset's class imbalance was addressed using weighted loss and data augmentation strategies. The models were trained for 50 epochs using Pytorch, achieving an image size of 224 × 224 pixels for both convolutional neural networks (CNNs) and the Swin Transformer. RESULTS: Our study compared six CNNs and the Swin Transformer for AIBD image classification, with the Swin Transformer achieving the highest average validation accuracy (98.5%). On a separate test set, the best model attained an accuracy of 94.6%, demonstrating 95.3% sensitivity and 97.5% specificity across AIBD classes. Visualization with Grad-CAM (class activation mapping) highlighted the model's reliance on characteristic patterns for accurate classification. CONCLUSIONS: The study highlighted the accuracy of CNNs in identifying DIF features. This approach aids automated analysis and reporting, offering reproducibility, speed, data handling and cost-efficiency. Integrating DL into skin immunofluorescence promises precise diagnostics and streamlined reporting in this branch of dermatology.

Artificial intelligence (AI) is transforming healthcare through machine and deep learning (computer systems that can learn and adapt, and make complex decisions, without receiving explicit instructions), improving disease management in dermatology, particularly in detecting skin cancer. However, AI's potential in automating immunofluorescence imaging in autoimmune bullous (blistering) skin diseases (AIBDs) remains largely untapped. Manual interpretation of direct immunofluorescence (DIF ­ a type of microscopy) can reduce efficiency. However, using deep learning to automatically classify DIF patterns (for example, the 'intercellular pattern' (ICP) and the 'linear pattern' (LP)) holds promise in helping with the diagnosis of AIBDs. This study aimed to develop AI algorithms for the automated classification of AIBD DIF patterns, such as ICP and LP, to improve diagnostic accuracy and streamline disease management. Immunofluorescence images were collected from skin biopsies of patients with a suspected AIBD between January 2022 and January 2024. Dermatologists classified the images into three categories: ICP, LP and negative. The dataset was divided into training (436 images) and test sets (93 images). A transfer learning framework (where what has been learned previously in one setting is used to improve performance in another) was used to make up for the limited amount of training data, to explore different models for the AIBD classification task. Our results revealed that a model called the 'Swin Transformer' achieved an average accuracy of 99% in diagnosing different AIBDs. The best model attained 95% accuracy on the test set and was reliable in identifying and ruling out different AIBDs. Visualization with Grad-CAM (a technique used in deep learning) highlighted the model's use of characteristic patterns to classify the diseases accurately. Overall, integrating deep learning in skin immunofluorescence promises to improve diagnostics and streamline reporting in dermatology, which could improve consistency, speed and cost-efficiency.

[Autoimmune bullous diseases in children]. / Dermatoses bulleuses auto-immunes chez les enfants.

Auto-immune bullous diseases (AIBD) are rare in children. Although their pathogenesis is similar to their adult counterpart, there are differences in the clinical presentation. Moreover certain AIBD prevail at certain ages. There are no guidelines for the treatment of AIBD specific for children. In this review the recent literature is summarised with attention to recent data including diagnostic criteria. We also propose a treatment algorithm.

Les maladies bulleuses auto-immunes (MBAI) sont rares chez les enfants. Bien que la pathogenèse soit similaire à celle de l'adulte, il existe des différences concernant la présentation clinique et la prévalence des MBAI selon l'âge. À ce jour, il n'y a pas de recommandations spécifiques pour leur prise en charge chez l'enfant. Dans cet article, nous présentons une revue des données actuelles, des critères diagnostiques et proposons un algorithme de prise en charge.

Lupus erythematosus-specific bullous lesions.

Lupus erythematosus (LE)-specific bullous lesions are often difficult to distinguish from other bullous diseases presenting in patients with systemic lupus erythematosus. Herein, we describe a 49-year-old woman with systemic lupus erythematosus with recurrent tense bullae on the forearms. Clinical, histopathologic, and serologic findings led to the diagnosis of LE-specific bullous lesions. We also summarize the diagnostic clues for distinguishing LE-specific bullous lesions, bullous systemic lupus erythematosus, and erythema multiforme-like lesions in LE (Rowell syndrome).

Diagnosis and Management of Bullous Disease.

Bullous diseases are a group of dermatoses primarily characterized by the presence of vesicles (0.1-0.9 cm) or bullae (>1 cm). There are various categories of bullous disease: allergic, autoimmune, infectious, mechanical, and metabolic. These diseases affect individuals in all decades of life, but older adults, age 65 and older, are particularly susceptible to bullous diseases of all etiologies. The incidence of these disorders is expected to increase given the advancing age of the general population. In this comprehensive review, we will outline the common bullous diseases affecting older individuals and provide an approach to evaluation and management.

Superficial and Bullous Neutrophilic Dermatoses: Sneddon-Wilkinson, IgA Pemphigus, and Bullous Lupus.

Sneddon-Wilkinson disease (SWD), IgA pemphigus, and bullous systemic lupus erythematosus (BSLE) are superficial and bullous neutrophilic dermatoses. They are all characterized by sterile neutrophilic infiltrate but differ in the level of skin affected and presence of autoantibodies. Both SWD and IgA pemphigus present with grouped flaccid pustules and have epidermal involvement; it is unclear whether they are distinct or exist on a spectrum of the same disease. IgA pemphigus is distinguished from SWD by positive direct immunofluorescence showing intercellular IgA deposition. BSLE presents with tense bullae, dermal neutrophilic infiltrate, and direct immunofluorescence showing linear IgG deposition along the dermal-epidermal junction.

State-of-the-art diagnosis of autoimmune blistering diseases.

Autoimmune blistering disorders (AIBDs) are a heterogeneous group of approximately a dozen entities comprising pemphigus and pemphigoid disorders and dermatitis herpetiformis. The exact diagnosis of AIBDs is critical for both prognosis and treatment and is based on the clinical appearance combined with the detection of tissue-bound and circulating autoantibodies. While blisters and erosions on the skin and/or inspectable mucosal surfaces are typical, lesions may be highly variable with erythematous, urticarial, prurigo-like, or eczematous manifestations. While direct immunofluorescence microscopy (IFM) of a perilesional biopsy is still the diagnostic gold standard, the molecular identification of the major target antigens opened novel therapeutic avenues. At present, most AIBDs can be diagnosed by the detection of autoantigen-specific serum antibodies by enzyme-linked immunosorbent assay (ELISA) or indirect IFM when the clinical picture is known. This is achieved by easily available and highly specific and sensitive assays employing recombinant immunodominant fragments of the major target antigens, i.e., desmoglein 1 (for pemphigus foliaceus), desmoglein 3 (for pemphigus vulgaris), envoplakin (for paraneoplastic pemphigus), BP180/type XVII collagen (for bullous pemphigoid, pemphigoid gestationis, and mucous membrane pemphigoid), laminin 332 (for mucous membrane pemphigoid), laminin ß4 (for anti-p200 pemphigoid), type VII collagen (for epidermolysis bullosa acquisita and mucous membrane pemphigoid), and transglutaminase 3 (for dermatitis herpetiformis). Indirect IFM on tissue substrates and in-house ELISA and immunoblot tests are required to detect autoantibodies in some AIBD patients including those with linear IgA disease. Here, a straightforward modern approach to diagnosing AIBDs is presented including diagnostic criteria according to national and international guidelines supplemented by long-term in-house expertise.

Management of Pustules and Vesicles in Afebrile Infants ≤60 Days Evaluated by Dermatology.

OBJECTIVES: To assess the management and outcomes of afebrile infants who received a pediatric dermatology consultation for pustules and/or vesicles. METHODS: Medical records were reviewed for all infants 60 days of age or younger who received a pediatric dermatology consult across 6 academic institutions between September 1, 2013 and August 31, 2019 to identify those infants with pustules and/or vesicles. RESULTS: Of the 879 consults, 183 afebrile infants presented with pustules and/or vesicles. No cerebrospinal fluid cultures or blood cultures were positive for bacteria. No concordant positive urine cultures were identified in infants with cutaneous infection. Nine infants were diagnosed with herpes simplex virus (HSV). Five preterm infants were diagnosed with angioinvasive fungal infections. CONCLUSIONS: No serious bacterial infections attributable to a skin source were identified, yet 53% of these infants received parenteral antibiotics. HSV was diagnosed in 7% of this cohort, 77.8% (7/9) of whom were term infants and 22.2% (2 of 9) of whom were preterm. Angioinvasive fungal infection was diagnosed in 3%, all of whom (100%, 5 of 5) were extremely preterm at <28 weeks gestational age. These findings suggest that in full-term afebrile infants ≤60 days, the likelihood of a life-threatening etiology of isolated pustules or vesicles is low once HSV infection is excluded. In preterm infants with pustules and/or vesicles, a high index of suspicion must be maintained, and broad infectious evaluation is recommended. HSV testing is recommended for all infants with vesicles, grouped pustules and/or punched-out erosions.

Generalized Pustular Psoriasis, Acute Generalized Exanthematous Pustulosis, and Other Pustular Reactions: A Clinical Review.

Generalized pustular rashes have various etiologies and can be challenging to diagnose and manage at first presentation. The authors provide an in-depth analysis of common pustular skin eruptions including generalized pustular psoriasis (GPP) and acute generalized exanthematous pustulosis, focusing on their pathophysiology, triggers, clinical presentation, diagnostic challenges, and management strategies. The article also highlights recent advances in genetic research and biologic therapies for GPP and the future directions in personalized medicine and prevention strategies.

Lesiones ampollares en una paciente con morfea panesclerótica discapacitante de la infancia / Bullous lesions in a patient with panesclerotic morphea of the childhood

La morfea ampollar es un tipo enfrecente de esclerodermia localizada que se caracteriza por presentar ampollas sobre placas escleróticas. La presencia de este tipo de lesiones obliga a descartar la variante extraenital de liquen esclerodemias localizadas, es posible hallar ambas afecciones. Se describe el caso de una paciente de 19 años con diagnóstico de morfea panesclerótica y liquen escleroso ampollar.

Bollous morphea is an infreqent type of morphea characterized for developing bullae on sclerodermiformic plaques. The presence of bullae forces to discard lichen sclerosus, a disease that usually develops in the genital zone, the extragenital variant could belong to the same spectrum that localized sclerodermiformic diseases. We present a 19 year old female patient with the diagnosis of panesclerotic morphea and bullous lichen sclerosus.

Subcorneal pustular dermatosis of Sneddon-Wilkinson

No disponible